Contextual Salience in Query-based Summarization

Discourse theories claim that text gets meaning in context. Most summarization systems do not take advantage of this. They assess the relevance of each passage individually rather than modeling the way context affects the relevance of passages. This paper presents a framework for graph-based summarization in order to model relations in text, so that the passages can be viewed in a broader context. The result is a summarization system which is more in line with discourse theory but still fully automatic. I evaluated the content selection performance of an implementation of the framework in different configurations. The system significantly outperforms a competitive baseline (and participant systems) on the DUC 2005 evaluation set.